This repository mainly contains the materials taught in this Reinforcement Learning course, which is offered in Spring 2018 at UW by Professor Pascal Poupart. The other part of this repository contains the project I involved during the course offering.
Most experiment is in [this] notebook.
- Markov Decision Process
- Reinforcement Learning
- Q-learning
- Policy Gradient
Note that this repository is only for personal learning purpose. The best practice to use this repository is to learn the algorithms taught in this course, instead of copying the code related to the assignment question. This repository has my implementations of the RL algorithms in the assignments, but my design is likely to be different than the starter code in the assignment. Please read it carefully.